© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 130834
    Prev
    Next
    INDEX
    Explanations

    proper nouns or names

    np_acts-logits-general · gemini-2.5-flash-lite

    questions about invoicING or money

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    д
    0.52
     ajoute
    0.51
     submits
    0.50
     זמן
    0.49
     submit
    0.48
     Fala
    0.48
     ለ
    0.48
     görünt
    0.47
     лиш
    0.47
     CtApp
    0.47
    POSITIVE LOGITS
    otoxicity
    0.52
     TEL
    0.47
    their
    0.46
    antum
    0.46
    양
    0.45
    好的
    0.44
    硒
    0.44
     governance
    0.43
    agas
    0.42
     tel
    0.42
    Activations Density 0.000%

    No Known Activations